CN106462964B - Method and digital microscope for being split to color image - Google Patents
Method and digital microscope for being split to color image Download PDFInfo
- Publication number
- CN106462964B CN106462964B CN201580023760.7A CN201580023760A CN106462964B CN 106462964 B CN106462964 B CN 106462964B CN 201580023760 A CN201580023760 A CN 201580023760A CN 106462964 B CN106462964 B CN 106462964B
- Authority
- CN
- China
- Prior art keywords
- color
- pixel
- image
- color image
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B21/00—Microscopes
- G02B21/36—Microscopes arranged for photographic purposes or projection purposes or digital imaging or video purposes including associated control and data processing arrangements
- G02B21/365—Control or image processing arrangements for digital or video microscopes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Optics & Photonics (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Color Image Communication Systems (AREA)
Abstract
The present invention relates to a kind of method being split to the color image being made of pixel, color image is for example shot with digital microscope and to be undergone and automatically analyzed.The invention further relates to a kind of digital microscopes, are able to carry out according to the method for the present invention using the digital microscope.Party's law regulation selects the color for representing the region to be split of color image first.According to providing the color and selected color that are associated with pixel based on tristimulus first color model.Determine wherein each pixel apart from size, this indicates the color and selected the distance between color according to the respective pixel of the first color model apart from size.The color for being associated with pixel and selected color are provided according to the second color model of sensing directional, determined thus for being associated with the color of pixel and at least each tone of selected color.When be associated with respective pixel apart from size under the threshold value that can be set when and when the tone for being associated with respective pixel is located in the section that can be set that is associated with around the tone of selected color, one of pixel is attached to the region divided.
Description
Technical field
Present invention firstly relates to a kind of method being split to the color image being made of pixel, color image for example with
Digital microscope shoots and to undergo and automatically analyzes.Moreover, it relates to which one kind can be executed according to the present invention using it
Method digital microscope.
Background technique
698 30 583 T2 of DE shows a kind of image processing method, receives input data, these are inputted
Data are divided into the basic unit of information.Show there HLS color space and RGB color for different types of analysis
Different adaptability.
According to the mesh for realizing identification object for analyzing the method for color image a kind of known in 44 19 395 A1 of DE
, wherein RGB image value is converted in HSI color space, to combine its color to execute the classification to each pixel.
102 39 801 A1 of DE teaches a kind of method for extracting structure feature from multichannel image.Implement according to second
Example forms feature for classification, on the one hand these features, are calculated in rgb space based on color distance size, another party
Face is calculated in the case where the binary mask that application produces herein in HSV space.
In Selvarasu, written " the Euclidean Distance Based Co1or Image of N et al.
Segmentation of Abnormality Detection from Pseudo Co1or Thermographs is (from pseudo- color
The color images based on Euclidean distance of the abnormality detection of color temperature logger) ", " international
Journal of Computer Theory and Engineering (international computer theory and engineering journal) ", volume 2,
4th phase, in August, 2010 describe the Euclidean distance for classifying to each pixel in 1793-8201 pages.At this
In document, representative pixel is selected, other each pixels is directed to using the pixel and calculates Euclidean distance.When distance is less than
Or when equal to threshold value determining in advance, retain the pixel, otherwise remove, to finally only can be appreciated that the area divided.Here, only
It is worked using a color space.Divide and is carried out according only to the threshold value apart from size.It is not concerned with the section for tone.
In Zakir, written " the Road sign segmentation based on colour Spaces:A of U et al.
Comparative Study (the road sign image segmentation based on color space: comparative study) ", " Proceedings of
The 11th lasted International Conference on Computer Graphics and Imaging (the
11 international computer figures and imaging proceeding) ", Innsbruck ,Austria describes hsv color space in 2010
Color value combined with the coloration of YUV color space by AND operation.Here, merely with the section for segmentation.
In Zhan, written " the A new method of color image segmentation based of Chi et al.
On intensity and hue clustering (new method based on the color images that intensity and form and aspect cluster) ",
Pattern Recognition (pattern-recognition), 2000, " Proceedings 15th International Conference
(the 15th international conference collection of thesis) ", volume 3, IEEE, being associated with for tone and intensity is described in 2000.Where it determines that being located at
These values within HSI color space.
Summary of the invention
From the prior art, task of the present invention is to improve to color image, especially by the colour of microscope photographing
The segmentation of image makes it further close to human perception.
The task is by the following method for being used to be split the color image being made of pixel of basis and passes through
Following digital microscope solves.
Method according to the present invention for being split to the color image being made of pixel the following steps are included:
Select the existing color in color image to be split, wherein the color represent the color image to
The region of segmentation；
It is associated with the color of pixel according to being provided based on tristimulus first color model and is selected in color image
Color out；
It determines for wherein each pixel apart from size, it is described to indicate apart from size according to first color model
Respective pixel color at a distance between the color selected in color image；
Examine whether the color selected in color image is achromaticity；
When the color selected in color image is achromaticity, the brightness of the color for being associated with pixel is determined
The brightness value of value and the color for being selected in color image；
When the color selected in color image be achromaticity when, and when be associated with respective pixel apart from size
When under the threshold value that can be set, and selected in color image when the brightness value that be associated with respective pixel is located at being associated with
When in the section that can be set around the brightness value of color out, one of pixel is attached to the region divided；
The color for being associated with pixel is provided according to the second color model of sensing directional and is selected in color image
Color determines the color and use for being associated with pixel thus when the color selected in color image is not achromaticity
In at least each tone for the color selected in color image；And
When the color selected in color image is not achromaticity, and when the distance for being associated with respective pixel is big
It is small under the threshold value that can be set when, and selected in color image when the tone that be associated with respective pixel is located at being associated with
When in the section that can be set around the tone of color out, one of pixel is attached to the region divided.
Digital microscope according to the present invention includes image capturing unit and the image that connect with described image shooting unit
Processing unit, described image processing unit are configured for executing according to the present invention for the cromogram being made of pixel
Method as being split.
According to the method for the present invention for especially by digital microscope shooting, the color image that is made of pixel from
Dynamic segmentation.Digital microscope is interpreted as following microscope herein, wherein user is not directed through object lens observation and is looked into microscope
The object seen, but microscope includes image capturing unit, especially electronic image converter.It is clapped using the image converter
The image taken the photograph is processed into digital information and is shown to user on display unit, especially monitor.This digital microscope
Have the function of automatically being used for image evaluation mostly, such as in the range of quality assurance and quality management (QA/QC).According to
Method of the invention more particularly to this image evaluation.
By segmentation, at least one region is determined in color image, which for example without background is shown in cromogram
As the object of interior imaging, so that the outline of object determines the boundary in region.At least one region divided can also indicate group
In pairs as or medium the component part being repeatedly imaged in color image.Therefore, this region divided is not usually square
Shape, but arbitrarily shape.The region also needs not be continuously, or determines the area wherein more divided by segmentation
Domain.In principle, region to be split can be following region, that is, it should be dedicated for further not assessing or just not
For further assessing.
In the method according to the invention, segmentation is implemented based on the color for being associated with pixel, these pixels can lead to respectively
Color position (Farbort) is crossed to describe.Therefore, include the following steps according to the method for the present invention, in this step, select generation
The color at least one region to be split of table color image.It is this to select preferably by user, especially at man-machine interface
It carries out.Multiple pixels in region to be split preferably have selected color or at least one close to selected color
Color.
In a step according to the method for the present invention, match according to based on tristimulus first color model to provide
Belong to the color and selected color of pixel.This tristimulus is preferably made of the three primary colors of additive color mixing method.Particularly preferably
, the first color model formed by RGB color model.Alternatively, the first color model for example passes through CMYK color model
Or similar color model is formed.Because RGB color model is widely used in image procossing, according to RGB color model
Additional consuming is not needed in most cases to provide the color for being associated with pixel and selected color, this is because this
The color image at place and selected color are described according to RGB color model.
In another step according to the method for the present invention, determine wherein each pixel apart from size.Apart from size point
The selected color according to described in the first color model of each pixel is not indicated and according to described by the first color model
The distance between color.It therefore, is selected color and respective pixel respectively apart from size according to the first color mould
The distance between the color in color space that type is constituted.
In particular it is preferred that being made of apart from size Euclidean distance.However it can also be using the distance of other measurements
Size.
It is realized in another step according to the method for the present invention, according to sensing directional
(wahrnehmungsorientiert) the second color model is associated with the color and selected color of pixel to provide.The
Parameter of the second colors model based on sensing directional, such as colouring information and luminance information.Colouring information includes tone and color saturation
Degree.Tone is also referred to as color value (Farbwert).According to the present invention, at least each color for the color for being associated with pixel is determined
The tone of color selected by reconciling.Second color model preferably passes through hsv color model and is formed.Second color model can also be with
It is formed by HSI color model, HSB color model or HSL color model, hsv color model is their common version.HSV
Color model includes the ingredient corresponding to tone for being referred to as " form and aspect (Hue) ".Therefore, in application hsv color model, at least
The form and aspect ingredient for the color and selected color for being associated with pixel is determined respectively.
In another step according to the method for the present invention, when being associated with capable of setting apart from size for respective pixel
When under threshold value, and when the tone for being associated with respective pixel is located at the energy around the tone for being associated with selected color
When in the section of setting, one of pixel is attached to the region divided.Two described conditions by logical AND that
This logic association, it is therefore necessary to meet the two conditions, thus respective pixel is attached to the region divided.Threshold value is preferred
It can be set by the user, particularly preferably be set at man-machine interface with interactive mode.Section, i.e. interval border preferably can also be by
User's setting, is particularly preferably set at man-machine interface with interactive mode.
It is preferred that the two conditions of all pixels are examined, so that they to be attached to the region divided respectively or is not attached
To the region divided.Therefore, when be associated with respective pixel apart from size under the threshold value that can be set when, and when matching
When belonging to the tone of respective pixel in the section that can be set around the tone for being associated with selected color, by it
In a pixel be attached to the region divided, preferred pin is to wherein each pixel.
Particular advantage according to the method for the present invention is: in terms of the adaptability for segmentation of different colours model
The advantages of having combined different colours model.The color model of sensing directional, such as hsv color model can be easily to the mankind
User illustrates, but the disadvantage is that: by selecting achromatic color, such as black, grey or white are come while obtaining all be used for
The possible tone of segmentation, this is inappropriate.And user is also difficult for these three constituent adjustment tones, color saturation
And brightness, to obtain desired color.Be based on tristimulus color model, such as the shortcomings that RGB color model: distance is big
It is small, such as Euclidean distance only partially corresponds to the distance of the human perception between two kinds of colors.By combining both not
It is the advantages of with color model, obvious closer to human perception according to the method for the present invention.According to the method for the present invention there are two tool
Parameter, that is, for the threshold value apart from size and for the section of tone, human user can intuitively and easily adjust it
, to obtain optimal result in segmentation.
A particularly preferred embodiment according to the method for the present invention further includes following steps, in this step, is examined
Whether selected color is achromaticity.When a certain color does not have tone, which is achromatic.Achromatic color is
Black, grey and white.Examine whether selected color is that achromaticity preferably carries out in the following way, that is, examine basis
Selected color described in first color model is directed to tristimulus value whether having the same, that is, for example, according to
Red, the green and blue value whether having the same for ingredient of selected color described in RGB color model.
In another step performed when selected color is achromaticity of the particularly preferred embodiment, determine
It is associated with the color of pixel and the brightness value of selected color out.Attach as a result, to each pixel and selected color bright
Angle value.The brightness value preferably passes through the ingredient for being referred to as " numerical value " of gray value or hsv color model or the quilt of HSI color model
The referred to as ingredient scene of " intensity ".
When selected color is achromaticity and respective pixel ought be associated in the particularly preferred embodiment
Apart from size under the threshold value that can be set when and when the brightness value that be associated with respective pixel be located at be associated with it is selected
When in the section that can be set around the brightness value of color out in performed another step, one of pixel is attached to
The region divided.The condition passes through logical AND logic association each other, to must satisfy all conditions, thus by respective picture
Element is attached to the region divided.Therefore, special conditional combination is applied in the case where selected color is achromatic situation,
Better result is obtained compared with the above-mentioned conditional combination based on tone in this case.In the brightness week of selected color
The section enclosed, the i.e. boundary in the section can be preferably set by the user, and particularly preferably be set at man-machine interface with interactive mode.
In the particularly preferred embodiment, it is above-mentioned provided according to the second color model be associated with pixel color and
The step of selected color is specifically the implementation when selected color is not achromaticity.
In the particularly preferred embodiment, it is above-mentioned when be associated with respective pixel apart from size in the threshold that can be set
When under value and when the tone for being associated with respective pixel is located at can set around the tone for being associated with selected color
When in fixed section, the step of one of pixel is attached to the region divided is specifically that work as selected color not non-
Implement when colored.
The advantages of particularly preferred embodiment is: pixel is under achromatic selected color regime with special
Mode is handled, and thus these pixels are more attached or are not attached in the mode harmonious with human perception and have been divided
The region cut.
When selected color is not achromaticity, and when being associated with capable of setting apart from size for respective pixel
When under threshold value, and when the tone for being associated with respective pixel is located at the energy around the tone for being associated with selected color
When in the section being set in advance, one of pixel is attached to the region divided, preferred pin carries out wherein each pixel.
Correspondingly, when selected color be achromaticity when, and when be associated with respective pixel apart from size in energy
When under the threshold value of setting, and when the brightness value for being associated with respective pixel is on weekly duty in the brightness for being associated with selected color
When in the section that can be set enclosed, one of pixel is attached to the region divided, preferred pin to wherein each pixel into
Row.
The color for being associated with pixel and selected color are provided according to the second color model preferably in the following way
Carry out, that is, be associated with the color according to described in RGB color model of pixel and according to described in RGB color model it is selected
Color out is converted into the description according to hsv color model respectively.Because RGB color model continues to extend in image procossing,
So it is associated with the color of pixel and most of selected color is present in the description according to RGB color model, therefore it
Can be transformed into from RGB color in hsv color space.
In another the step of preferably executing according to the method for the present invention, shows the color image divided or be at least
The region divided.Display preferably carries out on display unit, especially monitor.At least one region divided is preferably logical
Highlighting in color image is crossed, such as by false-color techniques (Falschfarbentechnik), or by not showing cromogram
Other regions of picture, or identify or show by only not showing the region divided.
The display in the region divided carries out preferably in graphic user interface, which is equally for selecting
A part of color to be selected and the man-machine interface for inputting threshold value and section out.User passes through man-machine interface preferred request
Color to be selected is selected first, then selects for the threshold value apart from size and then to select section, wherein it is preferred that with
Family otherwise be required under achromatic selected color regime adjust brightness value section or be required in not non-coloured silk
The section of tone is adjusted under the selected color regime of color.
For selecting for color, preferably show that figure selects tool to user, as such as the Eyedropper icon.For threshold value and area
Between adjusting, preferably to user show figure adjustment element, such as sliding control icon.Color is selected manually and manually adjusts tune
Whole element is preferably resulted in directly display and be selected or by changing color by changing threshold value or having been divided by what change section obtained
The region cut.It selects tool and adjustment element is preferably provided with predetermined value at the beginning.The predetermined value in respective section preferably passes through
As under type is adjusted, that is, so that the tone of the brightness of selected color or selected color is centrally located on corresponding area
In.
Digital microscope according to the present invention includes image capturing unit first, preferably passes through electronic image converter,
Such as ccd sensor or cmos sensor are formed.Digital microscope further includes image processing unit, is used to execute according to this hair
Bright method.Image processing unit can be structured as the whole component part of digital microscope.Image processing unit can also be with
Such as the calculator that can freely program by being associated with digital microscope is formed.Image processing unit is especially constructed to be used for
Realize preferred embodiment according to the method for the present invention.In terms of remaining, digital microscope according to the present invention preferably also has
Have above in conjunction with described feature according to the method for the present invention.
Digital microscope preferably includes display unit, such as is formed by monitor.Display unit is for showing with figure
As the image that shooting unit is shot, it is especially also used for the color image that display has been divided or the area that at least one of which has been divided
Domain.
It is also preferable to include man-machine interfaces for digital microscope, especially may be implemented to select the face for representing region to be split
Color, setting for apart from size threshold value and setting be located at section around the tone for being associated with selected color and
Setting is located at the section around the brightness value for being associated with selected color when necessary.Here, display unit preferably comprises people
A part of machine interface.In particular it is preferred that man-machine interface is constructed such that selecting color and given threshold and retouched
The variation when section stated directly affects the display in the region divided.
Detailed description of the invention
Other advantages, details and improved procedure combination attached drawing are by below to preferred implementation side according to the present invention according to the present invention
The description of case obtains.
Unique Fig. 1 shows the schematic flow chart of a preferred embodiment according to the method for the present invention.
Specific embodiment
Unique Fig. 1 shows the schematic flow chart of a preferred embodiment according to the method for the present invention.First
Color image be made of pixel, rgb format is provided in step, and user selects the existing color in color image,
The color is present in the color image region to be divided according to user intention.Therefore, user selects for region to be split
For be typical and prevailing color there.Here, region to be split needs not be continuous.
The image that color image is shot especially with digital microscope.
In a further step, distance map is formed in RGB color.In distance map, to each picture of color image
Element attaches the value for the Euclidean distance between the RGB color value of respective pixel and the RGB color value of selected color.
In the next step, the first stage of segmentation is executed.Examined for each pixel be associated with its Euclid away from
The threshold value for whether reaching from value or being not up to set by the user.Patrolling for parameter " subregion 1 " is obtained for each pixel as a result,
Collect value.
In the next step, examine whether selected color is gray scale, that is to say, that whether it is black, grey or white
Color, whether this is achromatic standard equity with selected color.In this case, red, green and blue ingredients
It is identical to be worth size.
In most cases, selected color does not have gray scale, that is to say, that be it is colored, thus carry out first color
Chromatic graph picture and selected color are from RGB color to the conversion in hsv color space.
But here, especially form and aspect ingredient, i.e. tonal content is most important to subsequent step, therefore can ignore other
Ingredient.
In the next step, the second stage of segmentation is executed.The form and aspect signal component value for being associated with it is examined for each pixel
Whether the upper interval border that is set by the user is higher than or lower than the lower interval border being set by the user, that is to say, that form and aspect signal component value
Whether in the section being set by the user.The section being set by the user includes the form and aspect signal component value of selected color.Needle as a result,
Logical value for parameter " subregion 2 " is obtained to each pixel.
In the next step, it is closed each other for the parameter " subregion 1 " of wherein each pixel and " subregion 2 " by logical "and"
Connection.When the parameter " subregion 1 " and parameter " subregion 2 " that are directed to related pixel are respectively logic " true "s, these pixels are matched respectively
Belong to the region divided.The region divided is set as a result, and is divided in this case with colored selected face
Color terminates.
In other cases, selected color is gray scale, that is, achromatic, it is first determined is directed to color image
Pixel and gray value for selected color, so as to also execute the second stage of segmentation in these cases.Point
This second stage cut is different from the above-mentioned second stage of the segmentation under not achromatic selected color regime
's.Here, under achromatic selected color regime, that is to say, that examine the gray value for being associated with it for each pixel
Whether the upper interval border that is set by the user is higher than or lower than the lower interval border being set by the user, that is to say, that whether is gray value
In the section being set by the user.The section being set by the user includes the gray value of selected color.It is directed to each picture as a result,
Element obtains the logical value for parameter " subregion 2 ".
In the next step, it is closed each other for the parameter " subregion 1 " of wherein each pixel and " subregion 2 " by logical "and"
Connection.When the parameter " subregion 1 " and parameter " subregion 2 " that are directed to related pixel are respectively logic " true "s, these pixels are matched respectively
Belong to the region divided.The region divided is set as a result, and is divided in this case with achromatic selected
Color terminates.
Whether it is gray scale independent of selected color, finally for example passes through highlighting or by not showing in color image
Show the remaining area of color image to show the region divided for user.
Claims (9)
1. the method for being split to the color image being made of pixel, the described method comprises the following steps:
Select the existing color in color image to be split, wherein the color represents the to be split of the color image
Region；
It is associated with the color of pixel according to being provided based on tristimulus first color model and is selected in color image
Color；
It determines for wherein each pixel apart from size, it is described to indicate apart from size according to each of first color model
From pixel color at a distance between the color selected in color image；
Examine whether the color selected in color image is achromaticity；
When the color selected in color image be achromaticity when, determine the color for being associated with pixel brightness value and
Brightness value for the color selected in color image；
When the color selected in color image be achromaticity when, and when be associated with respective pixel apart from size in energy
When under the threshold value of setting, and selected in color image when the brightness value that be associated with respective pixel is located at being associated with
When in the section that can be set around the brightness value of color, one of pixel is attached to the region divided；
The face that the color for being associated with pixel is provided according to the second color model of sensing directional and is selected in color image
Color is determined the color for being associated with pixel and is used for thus when the color selected in color image is not achromaticity
At least each tone for the color selected in color image；And
When the color selected in color image is not achromaticity, and works as and be associated with existing apart from size for respective pixel
When can be under the threshold value of setting, and be selected in color image when the tone that be associated with respective pixel is located at being associated with
When in the section that can be set around the tone of color, one of pixel is attached to the region divided.
2. the method according to claim 1, wherein being determined as follows the color for being associated with pixel
Brightness value and the color for being selected in color image brightness value, that is, determine the color for being associated with pixel
The gray value for the color that sum of the grayscale values is used to select in color image.
3. method according to claim 1 or 2, which is characterized in that examine selected in color image in the following way
Color whether be achromaticity, that is, examine the color selected in color image according to described in first color model
For tristimulus value whether having the same.
4. according to the method described in claim 3, it is characterized in that, first color model is formed by RGB color model.
5. according to the method described in claim 4, it is characterized in that, described formed apart from size by Euclidean distance.
6. according to the method described in claim 5, it is characterized in that, second color model is formed by hsv color model.
7. according to the method described in claim 6, it is characterized in that, the tone by the form and aspect of the hsv color model at
Divide and is formed.
8. digital microscope, the digital microscope includes image capturing unit and the image that connect with described image shooting unit
Processing unit, described image processing unit are configured for executing method according to any one of claim 1 to 7.
9. digital microscope according to claim 8, which is characterized in that the digital microscope further includes for showing
The display unit of the color image of segmentation.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102014106224.8A DE102014106224A1 (en) | 2014-05-05 | 2014-05-05 | Method for segmenting a color image and digital microscope |
| DE102014106224.8 | 2014-05-05 | ||
| PCT/EP2015/059417 WO2015169675A1 (en) | 2014-05-05 | 2015-04-29 | Method for segmenting a color image and digital microscope |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106462964A CN106462964A (en) | 2017-02-22 |
| CN106462964B true CN106462964B (en) | 2019-07-02 |
Family
ID=53199936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201580023760.7A Active CN106462964B (en) | 2014-05-05 | 2015-04-29 | Method and digital microscope for being split to color image |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US10083516B2 (en) |
| CN (1) | CN106462964B (en) |
| DE (1) | DE102014106224A1 (en) |
| WO (1) | WO2015169675A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107091800A (en) * | 2017-06-06 | 2017-08-25 | 深圳小孚医疗科技有限公司 | Focusing system and focus method for micro-imaging particle analysis |
| CN110807398A (en) * | 2019-10-28 | 2020-02-18 | 衢州学院 | Method and device for dividing field area |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686338A (en) * | 2008-09-26 | 2010-03-31 | 索尼株式会社 | System and method for partitioning foreground and background in video |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4419395C2 (en) | 1994-05-30 | 2000-09-28 | Graphikon Gmbh | Method and device for analyzing and processing color images |
| EP0989516B1 (en) | 1998-09-22 | 2005-06-15 | Hewlett-Packard Company, A Delaware Corporation | Image data processing method and corresponding device |
| DE10239801A1 (en) | 2002-08-29 | 2004-03-18 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Process for extracting texture features from a multi-channel image |
| JP4229980B1 (en) * | 2008-07-31 | 2009-02-25 | 国立大学法人広島大学 | Image segmentation apparatus and image segmentation method |
| US8861844B2 (en) * | 2010-03-29 | 2014-10-14 | Ebay Inc. | Pre-computing digests for image similarity searching of image-based listings in a network-based publication system |
-
2014
- 2014-05-05 DE DE102014106224.8A patent/DE102014106224A1/en active Pending
-
2015
- 2015-04-29 WO PCT/EP2015/059417 patent/WO2015169675A1/en active Application Filing
- 2015-04-29 CN CN201580023760.7A patent/CN106462964B/en active Active
- 2015-04-29 US US15/308,759 patent/US10083516B2/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686338A (en) * | 2008-09-26 | 2010-03-31 | 索尼株式会社 | System and method for partitioning foreground and background in video |
Non-Patent Citations (1)
| Title |
|---|
| Color Image Segmentation for Multimedia Applications;Ikonomakis N et al.;《Journal of Intelligent and Robotic Systems》;20060601;摘要第6-8行，第6页第6段第3-5行，第11页第2段第5-18行，第15页第2段 |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2015169675A1 (en) | 2015-11-12 |
| DE102014106224A1 (en) | 2015-11-05 |
| US10083516B2 (en) | 2018-09-25 |
| US20170116746A1 (en) | 2017-04-27 |
| CN106462964A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101283604B (en) | Image processing device with automatic white balance | |
| JP4935822B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN107862657A (en) | Image processing method, device, computer equipment and computer-readable recording medium | |
| KR20080016847A (en) | Methods of chromogen separation-based image analysis | |
| CN109923385B (en) | Method and apparatus for determining hair color uniformity | |
| US20130011036A1 (en) | Image processing apparatus, image reading apparatus, image processing method and information storage medium | |
| JP2006350740A (en) | Image processing apparatus and program thereof | |
| CN102088539B (en) | Method and system for evaluating pre-shot picture quality | |
| KR20200113853A (en) | System and Method for Determining Personal Color Analysis using Face Image Processing | |
| CN106558044A (en) | The resolution measuring method of image module | |
| CN106462964B (en) | Method and digital microscope for being split to color image | |
| CN111079637A (en) | Method, device and equipment for segmenting rape flowers in field image and storage medium | |
| JP7171549B2 (en) | Image analysis evaluation method, computer program, image analysis evaluation device | |
| US8817040B2 (en) | Methods for enhancing image quality | |
| US10602112B2 (en) | Image processing apparatus | |
| CN100504440C (en) | Tone adjustment method based on image overlap region for mosaic of remote sensing image | |
| CN111007020B (en) | Double-frame four-spectrum imaging method and application | |
| JP2009050035A (en) | Image processing method, image processing system, and image processing program | |
| US10175468B2 (en) | Method for generating a contrast image of an object structure and apparatuses relating thereto | |
| CN105654541B (en) | Video in window treating method and apparatus | |
| CN112995586A (en) | Image capturing method using color conversion and medical image capturing system | |
| EP3296960A1 (en) | A method and an arrangement for pseudo coloring of a digital image | |
| JP4392268B2 (en) | Surface inspection device | |
| JP2002117402A (en) | Image processing method and device thereof | |
| JP2008139101A (en) | Method and apparatus for extracting region becoming judge target of crystallized state from electronic image of protein solution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |